Abstract
In this paper, rotation invariance and the influence of rotation interpolation methods on texture recognition using several local binary patterns (LBP) variants are investigated. We show that the choice of interpolation method when rotating textures greatly influences the recognition capability. Lanczos 3 and B-spline interpolation are comparable to rotating the textures prior to image acquisition, whereas the recognition capability is significantly and increasingly lower for the frequently used third order cubic, linear and nearest neighbour interpolation. We also show that including generated rotations of the texture samples in the training data improves the classification accuracies. For many of the descriptors, this strategy compensates for the shortcomings of the poorer interpolation methods to such a degree that the choice of interpolation method only has a minor impact. To enable an appropriate and fair comparison, a new texture dataset is introduced which contains hardware and interpolated rotations of 25 texture classes. Two new LBP variants are also presented, combining the advantages of local ternary patterns and Fourier features for rotation invariance.
Highlights
In many computer vision and image analysis applications, the texture of an object is an important property that can be utilized for classification or segmentation procedures
We investigate and compare the following: local rotation invariance, global rotation invariance, including rotations in the training data, and the effect of the different interpolation methods when rotating textures, in the setting of retaining discriminant texture information
In analogy with the extension of local binary patterns (LBP) to improved local binary patterns (ILBP), where the neighbourhood mean value is used as the local threshold and the centre pixel is included in the code, local ternary pattern (LTP) can be extended to ILTP
Summary
In many computer vision and image analysis applications, the texture of an object is an important property that can be utilized for classification or segmentation procedures. In [7], a globally rotation invariant descriptor retaining distributions over orientations is introduced based on Fourier transformed responses from Gabor filter banks. We investigate and compare the following: local rotation invariance, global rotation invariance, including rotations in the training data, and the effect of the different interpolation methods when rotating textures, in the setting of retaining discriminant texture information. The dataset includes images of hardware-rotated textures as well as texture images rotated by the interpolation kernels: nearest neighbour, linear, third order cubic, cubic B-spline and Lanczos 3. The textured surfaces are rotated prior to image acquisition to allow for studying rotation invariance in texture analysis. For our purposes, undesirable artefacts in these rotation texture datasets (periodic stripes in Outex and JPEG compression in Mondial Marmi), a new dataset with rotations of textures was acquired. Interpolation of 2-D signals using Lanczos kernels was introduced in [17]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have